Dataset Information

Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network.

ABSTRACT:

Objective

We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images.

Materials and methods

Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation.

Results

The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model).

Conclusion

The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

SUBMITTER: Yoo SJ

PROVIDER: S-EPMC7909864 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network.

Yoo Seung Jin SJ Yoon Soon Ho SH Lee Jong Hyuk JH Kim Ki Hwan KH Choi Hyoung In HI Park Sang Joon SJ Goo Jin Mo JM

Korean journal of radiology 20201030 3

<h4>Objective</h4>We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images.<h4>Materials and methods</h4>Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchym ...[more]

PMID: 33169549

Similar Datasets

Project description:The purpose of this study was to develop an automated lung segmentation method for computerized detection of lung nodules in digital chest tomosynthesis.The authors collected 45 digital tomosynthesis scans and manually segmented reference lung regions in each scan to assess the performance of the method. The authors automated the technique by calculating the edge gradient in an original image for enhancing lung outline and transforming the edge gradient image to polar coordinate space. The authors then employed a dynamic programming technique to delineate outlines of the unobscured lungs in the transformed edge gradient image. The lung outlines were converted back to the original image to provide the final segmentation result. The above lung segmentation algorithm was first applied to the central reconstructed tomosynthesis slice because of the absence of ribs overlapping lung structures. The segmented lung in the central slice was then used to guide lung segmentation in noncentral slices. The authors evaluated the segmentation method by using (1) an overlap rate of lung regions, (2) a mean absolute distance (MAD) of lung borders, (3) a Hausdorff distance of lung borders between the automatically segmented lungs and manually segmented reference lungs, and (4) the fraction of nodules included in the automatically segmented lungs.The segmentation method achieved mean overlap rates of 85.7%, 88.3%, and 87.0% for left lungs, right lungs, and entire lungs, respectively; mean MAD of 4.8, 3.9, and 4.4 mm for left lungs, right lungs, and entire lungs, respectively; and mean Hausdorrf distance of 25.0 mm, 25.5 mm, and 30.1 mm for left lungs, right lungs, and entire lungs, respectively. All of the nodules inside the reference lungs were correctly included in the segmented lungs obtained with the lung segmentation method.The method achieved relatively high accuracy for lung segmentation and will be useful for computer-aided detection of lung nodules in digital tomosynthesis.

Project description:Lung segmentation is a fundamental step in many image analysis applications for lung diseases and abnormalities in thoracic computed tomography (CT). The authors have previously developed a lung segmentation method based on expectation-maximization (EM) analysis and morphological operations (EMM) for our computer-aided detection (CAD) system for pulmonary embolism (PE) in CT pulmonary angiography (CTPA). However, due to the large variations in pathology that may be present in thoracic CT images, it is difficult to extract the lung regions accurately, especially when the lung parenchyma contains extensive lung diseases. The purpose of this study is to develop a new method that can provide accurate lung segmentation, including those affected by lung diseases.An iterative neutrosophic lung segmentation (INLS) method was developed to improve the EMM segmentation utilizing the anatomic features of the ribs and lungs. The initial lung regions (ILRs) were extracted using our previously developed EMM method, in which the ribs were extracted using 3D hierarchical EM segmentation and the ribcage was constructed using morphological operations. Based on the anatomic features of ribs and lungs, the initial EMM segmentation was refined using INLS to obtain the final lung regions. In the INLS method, the anatomic features were mapped into a neutrosophic domain, and the neutrosophic operation was performed iteratively to refine the ILRs. With IRB approval, 5 and 58 CTPA scans were collected retrospectively and used as training and test sets, of which 2 and 34 cases had lung diseases, respectively. The lung regions manually outlined by an experienced thoracic radiologist were used as reference standard for performance evaluation of the automated lung segmentation. The percentage overlap area (POA), the Hausdorff distance (Hdist), and the average distance (AvgDist) of the lung boundaries relative to the reference standard were used as performance metrics.The proposed method achieved larger POAs and smaller distance errors than the EMM method. For the 58 test cases, the average POA, Hdist, and AvgDist were improved from 85.4±18.4%, 22.6±29.4 mm, and 3.5±5.4 mm using EMM to 91.2±6.7%, 16.0±11.3 mm, and 2.5±1.0 mm using INLS, respectively. The improvements were statistically significant (p<0.05). To evaluate the accuracy of the INLS method in the identification of the lung boundaries affected by lung diseases, the authors separately analyzed the performance of the proposed method on the cases with versus without the lung diseases. The results showed that the cases without lung diseases were segmented more accurately than the cases with lung diseases by both the EMM and the INLS methods, but the INLS method achieved better performance than the EMM method in both cases.The new INLS method utilizing the anatomic features of the rib and lung significantly improved the accuracy of lung segmentation, especially for the cases affected by lung diseases. Improvement in lung segmentation will facilitate many image analysis tasks and CAD applications for lung diseases and abnormalities in thoracic CT, including automated PE detection.

Project description:ObjectiveChest computed tomography (CT) imaging is being increasingly used for potential lung donor assessment. However, the efficacy of CT imaging in this setting remains unknown. We hypothesize that chest CT imaging independently affects the decision-making process in donor lung utilization.MethodsWe conducted a retrospective cohort study of all adult donation after brain death donors managed through our local organ procurement organization from June 2011 to November 2016. An experienced thoracic radiologist independently reviewed donor chest CT and chest x-ray images in a blinded, standardized manner to determine the presence of structural lung disease (eg, emphysema, interstitial lung disease [ILD]) and acute abnormalities (eg, traumatic lung injury [TLI]). Distinct models of lung utilization were fit to groups with initial partial pressure of oxygen (iPaO2) ≤300 mm Hg (suboptimal) and iPaO2 >300 mm Hg (optimal).ResultsThe organ procurement organization managed 753 donors during the study period, with a lung utilization rate ([lung donors/all organ donors] × 100) of 36.5% (275 of 753). Four hundred forty-five (59.1%) donors received chest CT imaging, revealing emphysema (13.7%), ILD (2.5%), and TLI (7.2%). In univariate analysis, findings of TLI (odds ratio [OR], 2.23; 95% confidence interval [CI], 1.08-4.61) were positively associated with lung utilization, whereas findings of emphysema (OR, 0.18; CI, 0.08-0.40) were negatively associated with utilization. In multivariate analysis, CT findings of emphysema (OR, 0.21; CI 0.08-0.54) remained negatively associated with utilization. No potential donors with CT findings of ILD became lung donors. After controlling for chest x-ray findings, chest CT imaging findings of structural lung disease remained negatively associated with utilization (P = .0001). Lung utilization rate in the suboptimal and optimal iPaO2 populations was 35.1% and 41.4%, respectively, and CT findings of emphysema had a significant association with nonutilization in both groups.ConclusionsIn the evaluation of potential lung donors, chest CT imaging findings of structural lung disease, such as emphysema and ILD, have a significant negative association with lung utilization. Our findings suggest that chest CT imaging might be an important adjunct to conventional lung donor assessment criteria.

Dataset Information

Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network.

Objective

Materials and methods

Results

Conclusion

Publications

Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure